# Plugin Networks for Inference under Partial Evidence

## TL;DR

This paper introduces Plugin Networks, a new approach that adds simple modules to pre-trained CNNs to incorporate partial evidence during inference, improving performance across various tasks efficiently.

## Contribution

The paper presents Plugin Networks, a novel, efficient method for integrating partial evidence into CNN inference by attaching lightweight modules to intermediate layers.

## Key findings

- Outperforms state-of-the-art methods in scene categorization
- Enhances multi-label image annotation accuracy
- Improves semantic segmentation results

## Abstract

In this paper, we propose a novel method to incorporate partial evidence in the inference of deep convolutional neural networks. Contrary to the existing, top performing methods, which either iteratively modify the input of the network or exploit external label taxonomy to take the partial evidence into account, we add separate network modules ("Plugin Networks") to the intermediate layers of a pre-trained convolutional network. The goal of these modules is to incorporate additional signal, ie information about known labels, into the inference procedure and adjust the predicted output accordingly. Since the attached plugins have a simple structure, consisting of only fully connected layers, we drastically reduced the computational cost of training and inference. At the same time, the proposed architecture allows to propagate information about known labels directly to the intermediate layers to improve the final representation. Extensive evaluation of the proposed method confirms that our Plugin Networks outperform the state-of-the-art in a variety of tasks, including scene categorization, multi-label image annotation, and semantic segmentation.